Probing for Consciousness in Machines
It addresses the problem of understanding and potentially replicating consciousness in machines, which is foundational for AI, but the approach is incremental as it builds on existing theories and methods.
This study investigated whether artificial agents can develop core consciousness by training a reinforcement learning agent in a virtual environment to play a video game, and found that the agent formed rudimentary world and self models as measured by probes predicting its spatial positions.
This study explores the potential for artificial agents to develop core consciousness, as proposed by Antonio Damasio's theory of consciousness. According to Damasio, the emergence of core consciousness relies on the integration of a self model, informed by representations of emotions and feelings, and a world model. We hypothesize that an artificial agent, trained via reinforcement learning (RL) in a virtual environment, can develop preliminary forms of these models as a byproduct of its primary task. The agent's main objective is to learn to play a video game and explore the environment. To evaluate the emergence of world and self models, we employ probes-feedforward classifiers that use the activations of the trained agent's neural networks to predict the spatial positions of the agent itself. Our results demonstrate that the agent can form rudimentary world and self models, suggesting a pathway toward developing machine consciousness. This research provides foundational insights into the capabilities of artificial agents in mirroring aspects of human consciousness, with implications for future advancements in artificial intelligence.